CN112836128A - Information recommendation method, device, equipment and storage medium - Google Patents
Information recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112836128A CN112836128A CN202110185074.7A CN202110185074A CN112836128A CN 112836128 A CN112836128 A CN 112836128A CN 202110185074 A CN202110185074 A CN 202110185074A CN 112836128 A CN112836128 A CN 112836128A
- Authority
- CN
- China
- Prior art keywords
- sample
- information
- recommendation
- test
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an information recommendation method, an information recommendation device, information recommendation equipment and a storage medium. The method comprises the following steps: acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended; inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing; and recommending information to the current user according to each piece of predicted behavior data. Because the recommendation model for information recommendation is obtained by training based on the sample data set subjected to noise reduction processing, the overall prediction performance of the recommendation model is high, and the accuracy of information recommendation is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of internet, in particular to an information recommendation method, device, equipment and storage medium.
Background
With the continuous development of big data technology, various information explosively increases, and information can be pushed for a user more accurately through big data analysis. Taking information as an advertisement as an example, behavior data generated by a user aiming at the advertisement after the user sees the advertisement can be predicted through a recommendation model. Therefore, it is crucial to train an accurate recommendation model. However, behavior data generated by the user for the advertisement is often provided by a third-party platform, and errors may be generated by the third-party platform when the third-party platform returns data, so that the part of data carries high noise, and the prediction performance of the trained recommendation model is poor.
Disclosure of Invention
The invention provides an information recommendation method, device, equipment and storage medium, aiming at the technical problem that the prediction performance of a recommendation model in the prior art is poor.
In a first aspect, an embodiment of the present invention provides an information recommendation method, including:
acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended;
inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and recommending information to the current user according to each piece of predicted behavior data.
In a second aspect, an embodiment of the present invention provides an information recommendation apparatus, including:
the first acquisition module is used for acquiring the user characteristics of the current user and the information characteristics of each piece of information to be recommended;
the prediction module is used for inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and the recommending module is used for recommending information to the current user according to each piece of predicted behavior data.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the information recommendation method provided in the first aspect of the embodiment of the present invention when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the information recommendation method provided in the first aspect of the embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, the user characteristics of the current user and the information characteristics of each piece of information to be recommended are obtained, the user characteristics and the information characteristics are input into a preset recommendation model, the predicted behavior data of the current user on each piece of information to be recommended is obtained, and information recommendation is carried out on the current user according to each piece of predicted behavior data. The recommendation model for information recommendation is obtained by training based on the sample data set subjected to noise reduction, namely in the training process of the recommendation model, the noise reduction is performed on the sample data set, so that the noise carried by the sample data set subjected to noise reduction is greatly reduced, the influence of the noise on the recommendation model training is reduced, the overall prediction performance of the recommendation model is improved, and the accuracy of information recommendation is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
Fig. 1 is a schematic flowchart of an information recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a training process of a recommendation model according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a noise reduction processing method for a sample tag according to an embodiment of the present invention;
FIG. 4 is a scatter plot of a first recommendation model trained using an original sample data set;
fig. 5 is a scatter diagram of a second recommendation model obtained by training using a sample data set after noise reduction processing according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a process for determining a target clustering parameter and a target partition ratio according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
In the conventional technology, the average square error is generally adopted as an objective loss function, and the training of the recommendation model is performed by using a large amount of sample data sets. However, the sample labels in the sample data set are often provided by a third-party platform, so that the acquired sample labels carry high noise, and thus, in the process of training the recommendation model by using the sample data set, the recommendation model is biased to learn noise instead of learning a real label value, so that the overall prediction performance of the recommendation model is reduced. Therefore, the technical scheme provided by the embodiment of the invention can improve the overall prediction performance of the recommendation model, and further improve the accuracy of information recommendation.
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments of the present invention may be arbitrarily combined with each other without conflict.
It should be noted that the execution subject of the method embodiments described below may be an information recommendation apparatus, which may be implemented as part of or all of an electronic device by software, hardware, or a combination of software and hardware. Optionally, the electronic device may be a client, including but not limited to a smart phone, a tablet computer, a vehicle-mounted terminal, and the like. Of course, the electronic device may also be an independent server or a server cluster, and the embodiment of the present invention does not limit the specific form of the electronic device. The method embodiments described below are described by taking as an example that the execution subject is an electronic device.
Fig. 1 is a schematic flow chart of an information recommendation method according to an embodiment of the present invention. The embodiment relates to a specific process of how the electronic device carries out information recommendation to a user. As shown in fig. 1, the method may include:
s101, obtaining user characteristics of a current user and information characteristics of each piece of information to be recommended.
The current user is a user of information to be recommended. The information to be recommended can be videos to be recommended, audios to be recommended, advertisements to be recommended, articles to be recommended and the like. The user characteristics authorized by the current user may include nationality, gender, age, hobby and the like of the user, and the information characteristics of the information to be recommended may include brand, category, price, material, historical statistical information and the like of the information. In practical application, before acquiring the user characteristics of the current user, the electronic device sends prompt information to the current user, where the prompt information is used to ask whether the acquisition permission of the user characteristics needs to be opened. After obtaining the confirmation instruction of the user, the electronic device will obtain the user characteristics authorized by the current user.
When information recommendation needs to be performed on a current user, user characteristics authorized by the current user can be obtained from the database, a plurality of pieces of information are randomly selected from the database or selected according to a preset selection rule to serve as information to be recommended, and information characteristics of each piece of information to be recommended are obtained from the database.
S102, inputting the user characteristics and the information characteristics into a preset recommendation model to obtain the predicted behavior data of the current user on the information to be recommended.
And the recommendation model is obtained by training based on the sample data set subjected to noise reduction processing. The sample data set comprises a plurality of sample labels subjected to noise reduction processing, and the sample labels are behavior data generated by sample users on the display information. The predicted behavior data may be click behavior data (such as click probability or click times) of the current user on each piece of information to be recommended, purchase behavior data, payment value data, viewing behavior data, and the like.
After obtaining the user characteristics authorized by the current user and the information characteristics of each piece of information to be recommended, the electronic equipment inputs the user characteristics authorized by the current user and the information characteristics of each piece of information to be recommended into a pre-trained recommendation model, and predicts the predicted behavior data generated by the current user on each piece of information to be recommended through the recommendation model.
S103, recommending information to the current user according to the predicted behavior data.
After the predicted payment data of each piece of information to be recommended is obtained, the electronic equipment can recommend the information to be recommended, of which the predicted behavior data is larger than a preset threshold value, to the current user. Optionally, the electronic device may further sort the predicted behavior data, and recommend information to the current user based on the sorted result. Taking the predicted behavior data as the predicted payment data as an example, the electronic equipment sorts the predicted payment data and recommends the information to be recommended with the highest predicted payment data to the current user.
According to the technical scheme provided by the embodiment of the invention, the user characteristics of the current user and the information characteristics of each piece of information to be recommended are obtained, the user characteristics and the information characteristics are input into a preset recommendation model, the predicted behavior data of the current user on each piece of information to be recommended is obtained, and information recommendation is carried out on the current user according to each piece of predicted behavior data. The recommendation model for information recommendation is obtained by training based on the sample data set subjected to noise reduction, namely in the training process of the recommendation model, the noise reduction is performed on the sample data set, so that the noise carried by the sample data set subjected to noise reduction is greatly reduced, the influence of the noise on the recommendation model training is reduced, the overall prediction performance of the recommendation model is improved, and the accuracy of information recommendation is improved.
In one embodiment, a training process for a recommendation model is also provided. On the basis of the foregoing embodiment, optionally, before the foregoing S101, as shown in fig. 2, the method further includes:
s201, obtaining an original sample data set.
The original sample data set comprises a plurality of sample labels, and the sample labels are behavior data generated by sample users for the display information. The display information may be videos, advertisements, audios, commodities, and the like, which have been displayed to the sample user. The original sample data set may include a plurality of corresponding input sample data and output sample data. The input sample data comprises user characteristics authorized by the sample user and information characteristics of various display information, the user characteristics can comprise nationality, gender, age, hobbies and the like of the user, and the information characteristics can comprise brands, categories, prices, materials, historical statistical information and the like of the information. The output sample data includes sample tags, such as original click data, original payment data, or original viewing data.
Optionally, the electronic device may obtain the presentation log and the behavior log, and generate an original sample data set according to the presentation log and the behavior log. Specifically, the electronic device obtains a sample label based on the display log and the behavior log, and then extracts a user feature corresponding to the identifier of the sample user from the database, and extracts an information feature corresponding to the identifier of the display information. And then, taking the extracted user characteristics of the sample user and the information characteristics of the display information as input sample data, and taking a sample label corresponding to the input sample data as output sample data, thereby forming an original sample data set.
S202, denoising all the sample labels to obtain a denoised sample data set.
Generally, the sample tags are provided by a third-party platform, and errors may occur in the data in the return process or the third-party platform lacks corresponding technical support, so that the sample tags acquired by the electronic device carry high noise and cannot reflect real behavior data, that is, error data exists in a plurality of sample tags. Taking the sample label as the payment data generated by the sample user for the presentation information as an example, it is assumed that the real payment data generated by the sample user for the presentation information is 50 yuan, but for the above reasons, the payment data returned to the electronic device by the third-party platform is 30 yuan, so that if the recommendation model is trained directly with the returned payment data, the model tends to learn the random label when the gradient descent gain caused by the correct payment data is not enough to counter the influence of the wrong payment data in the model training process. When the amount of wrong payment data is close to the amount of correct payment data, it is difficult to train a model with higher prediction performance.
Therefore, the electronic device needs to perform noise reduction processing on all sample tags, so that noise carried by the processed sample tags is greatly reduced. Assuming that the noise carried by the sample label is subjected to Gaussian distribution with a mean value of zero and a variance of a, a certain noise reduction method is adopted to perform noise reduction processing on all the sample labels, so that the variance of the noise carried by the processed sample label is smaller than a. Because the variance of the noise carried by the processed sample label is less than a, the processed sample label is closer to the real behavior data, and thus, when the recommendation model is trained by adopting the sample data set subjected to noise reduction processing, the influence of the noise on the training of the recommendation model is greatly reduced.
Optionally, the electronic device may perform noise reduction processing on all sample tags in a manner described in the following embodiments. Specifically, referring to fig. 3, the step S202 may be:
s301, dividing a data range formed by all the sample labels into a plurality of sample intervals according to the preset target clustering number and the preset target division ratio.
The target clustering number may be understood as the number of sample intervals into which a data range formed by all sample labels is divided, and the target division ratio may be understood as a ratio of each divided sample interval to an interval width. For example, assuming that the data range formed by all the sample labels is 1, the number of the object clusters is 3, and the object division ratio is 3: 5: and 2, the electronic equipment divides the data range formed by all the sample labels into 3 sample intervals based on the target clustering number and the target division ratio, wherein the divided sample intervals are [0,0.3], [0.3,0.8] and [0.8,1] in sequence.
S302, aiming at each sample interval, modifying the sample label in the sample interval into a first target value in the sample interval.
Wherein, for each sample interval, the electronic device can modify all sample labels located in the sample interval to the first target value within the sample interval. The first target value may be any one of the sample labels within the sample interval. Of course, the first target value may also be a median of the sample interval, an average of all sample labels within the sample interval, or a median of all sample labels within the sample interval.
Continuing with the example in S301, and assuming that the first target value is the middle value of the sample interval, for sample interval [0,0.3], the electronic device modifies all sample tags located within [0,0.3] to 0.15, for sample interval [0.3,0.8], the electronic device modifies all sample tags located within [0.3,0.8] to 0.55, and for sample interval [0.8,1], the electronic device modifies all sample tags located within [0.8,1] to 0.9.
The noise reduction principle of the noise reduction processing mode is as follows: the noise carried by the sample label itself is assumed to be zero on the mean and the variance is gaussian of the first value. After the interval division is performed, and each sample label in the divided sample interval is clustered into the first target value in the sample interval, uncertainty caused by clustering optimization is introduced, and the uncertainty can be regarded as one-half of the interval width of the sample interval. Therefore, it can be considered that the noise carried by the sample label after the clustering operation is subject to a gaussian distribution with a mean value of zero and a variance of a second value, wherein the second value is one half of the interval width of the sample interval. The target clustering quantity and the target division ratio are obtained through a plurality of test experiments and are configured in the electronic equipment in advance, so that the second numerical value is smaller than the first numerical value. Therefore, when the model is trained, the electronic equipment divides the sample interval based on the target clustering number and the target division proportion, modifies all sample labels in the sample interval into the same target value, and makes the variance of the noise carried by the processed sample labels smaller than the variance of the noise carried by the unprocessed sample labels after all the sample labels are processed in the noise reduction mode, so that the influence of the noise on the model training is reduced.
In order to verify the effect of the technical scheme provided by the embodiment of the invention, taking a sample label as a sample, and taking payment data generated by a user on display information as an example, two model training results are compared, wherein the first model comprises the following steps: predicting the payment data by using a first recommendation model obtained by training an original sample data set, and secondly: and predicting the payment data by using a second recommendation model obtained by training the sample data set subjected to the noise reduction processing in the noise reduction processing mode. As shown in fig. 4 and 5, it is apparent from the two graphs that the overall prediction performance of the second recommendation model is in an "upward" trend compared with the first recommendation model.
S203, training a preset basic model according to the sample data set subjected to the noise reduction processing to obtain the recommended model.
After denoising all the sample labels, the electronic equipment takes the user characteristics of the sample users and the information characteristics of the display information as input, takes the denoised sample labels as expected output of a preset basic model, and trains the basic model by adopting a preset target loss function, so that a recommended model is obtained. The model structure of the basic model is the same as that of the recommended model. Alternatively, the target loss function may be an average square error loss function or a band parameter loss function.
Specifically, model parameters of the basic model are initialized, user characteristics of the sample user and information characteristics of the display information are input into the initialized basic model, predicted behavior data of the sample user on the display information is determined through the basic model, and a loss value of the target loss function is determined based on the predicted behavior data and actual behavior data (the actual behavior data is the sample label after the noise reduction processing). And when the loss value is greater than a preset threshold value, updating parameters of each layer of the basic model, and continuing training the updated basic model based on the sample data set subjected to the noise reduction processing until the loss value of the target loss function is less than or equal to the preset threshold value, so that a trained recommended model is obtained.
In this embodiment, an original sample data set is obtained, and noise reduction processing is performed on all sample tags in the original sample data set to obtain a processed sample data set; and training a preset basic model according to the processed sample data set to obtain a recommended model. In the training process of the recommendation model, noise reduction processing is performed on all sample labels, so that noise carried by all sample labels is greatly reduced, the influence of the noise on the training of the recommendation model is reduced, and the overall prediction performance of the recommendation model is improved.
Because the target clustering number and the target division ratio used in the noise reduction processing are obtained through a plurality of test experiments, the variance of the noise carried by the sample label after interval division can be smaller than the variance of the noise carried by the unprocessed sample label. Therefore, the embodiment of the application also provides a process for determining the number of the target clusters and the target division ratio. On the basis of the foregoing embodiment, optionally, as shown in fig. 6, the determining process of the number of target clusters and the target division ratio may be:
s601, setting a plurality of groups of test parameters.
Wherein the test parameters include an initial cluster number and an initial partition ratio. The initial cluster number may be understood as an initial number of sample intervals into which a data range formed by all sample labels is divided, and the initial division ratio may be understood as an initial ratio for an interval width between the divided sample intervals.
S602, respectively based on the test parameters, carrying out noise reduction processing on the sample labels in the sample data sets to obtain a plurality of test sample data sets.
Specifically, for each set of test parameters, the electronic device may perform noise reduction processing on all sample tags by using a certain noise reduction method based on the test parameters. As an alternative implementation, the process of S602 may be: and aiming at each group of test parameters, dividing the data range formed by all the sample labels into a plurality of test sample intervals according to the test parameters, and modifying the sample labels positioned in the test sample intervals into second target values in the test sample intervals to obtain a test sample data set.
The second target value may be any sample label within the test sample interval. Of course, the second target value may also be a middle value of the test sample interval, an average value of all sample tags within the test sample interval, or a median of all sample tags within the test sample interval.
It should be noted that, as for the specific process in S602, reference may be made to the specific description in S301 to S302, and this embodiment is not described herein again.
S603, training the basic model based on the test sample data set respectively to obtain a plurality of test recommendation models.
According to each test sample data set, the electronic equipment takes the user characteristics of the sample users and the information characteristics of the display information in the test sample data set as input, takes the sample labels subjected to noise reduction processing as expected output, and trains a preset basic model by adopting a preset target loss function, so that a test recommendation model is obtained.
S604, calculating the performance scores of the test recommendation models, and determining the test parameters corresponding to the test recommendation models with the performance scores meeting preset conditions as the target clustering number and the target division ratio.
The performance score can reflect the prediction performance of each test recommendation model, and in practical application, the performance evaluation of each test recommendation model can be realized by calculating the Area Under the ROC Curve (AUC) score of each test recommendation model. After the test recommendation models corresponding to the multiple groups of test parameters are obtained, the electronic equipment respectively calculates the AUC scores of the test recommendation models, determines the initial clustering number corresponding to the test recommendation model with the AUC score meeting the preset conditions as the target clustering number, and determines the initial division ratio corresponding to the test recommendation model with the AUC score meeting the preset conditions as the target division ratio. Optionally, the electronic device may determine the test parameter corresponding to the test recommendation model with the highest AUC score as the target cluster number and the target division ratio.
It can be understood that, because the AUC score of the test recommendation model corresponding to the determined target cluster number and the target partition ratio is the highest, that is, higher than the AUC score of the recommendation model trained by using the original sample data set that is not subjected to the noise reduction processing, at this time, it may be considered that the variance of the noise carried by the processed sample tags is smaller than the variance of the noise carried by the unprocessed sample tags after the data range formed by all the sample tags is subjected to interval partition by using the target cluster number and the target partition ratio and each sample tag in the sample interval is modified to the first target value in the sample interval.
In this embodiment, the electronic device divides a data range formed by all sample tags in the sample data set into a plurality of sample intervals according to the target clustering number and the target division ratio, and modifies, for each sample interval, the sample tags located in the sample interval into the first target value in the sample interval. Because the variance of the noise carried by the interval-divided sample labels is smaller than the variance of the noise carried by the unprocessed sample labels by the target clustering quantity and the target division proportion, the noise carried by the processed sample labels is greatly reduced after all the sample labels are processed by the noise reduction mode, the recommendation model is prevented from being biased to learning noise in the training process, namely, the influence of the noise on model training is reduced, and the overall prediction performance of the recommendation model is improved.
Fig. 7 is a schematic structural diagram of an information recommendation apparatus according to an embodiment of the present invention. As shown in fig. 7, the apparatus may include: a first obtaining module 701, a predicting module 702 and a recommending module 703.
Specifically, the first obtaining module 701 is configured to obtain a user characteristic of a current user and an information characteristic of each piece of information to be recommended;
the prediction module 702 is configured to input the user characteristics and the information characteristics into a preset recommendation model, so as to obtain predicted behavior data of the current user on each piece of information to be recommended, where the recommendation model is obtained by training based on a sample data set after noise reduction processing;
the recommending module 703 is configured to recommend information to the current user according to each piece of predicted behavior data.
According to the technical scheme provided by the embodiment of the invention, the user characteristics of the current user and the information characteristics of each piece of information to be recommended are obtained, the user characteristics and the information characteristics are input into a preset recommendation model, the predicted behavior data of the current user on each piece of information to be recommended is obtained, and information recommendation is carried out on the current user according to each piece of predicted behavior data. The recommendation model for information recommendation is obtained by training based on the sample data set subjected to noise reduction, namely in the training process of the recommendation model, the noise reduction is performed on the sample data set, so that the noise carried by the sample data set subjected to noise reduction is greatly reduced, the influence of the noise on the recommendation model training is reduced, the overall prediction performance of the recommendation model is improved, and the accuracy of information recommendation is improved.
On the basis of the foregoing embodiment, optionally, the apparatus further includes: the device comprises a second acquisition module, a noise reduction module and a training module.
Specifically, the second obtaining module is configured to obtain an original sample data set before the first obtaining module 701 obtains the user characteristics of the current user and the information characteristics of each piece of information to be recommended, where the original sample data set includes a plurality of sample tags, and the sample tags are behavior data generated by the sample user for displaying the information;
the noise reduction module is used for carrying out noise reduction processing on all sample labels to obtain a sample data set subjected to noise reduction processing;
and the training module is used for training a preset basic model according to the sample data set subjected to the noise reduction processing to obtain the recommendation model.
On the basis of the above embodiment, optionally, the noise reduction module is specifically configured to divide a data range formed by all the sample labels into a plurality of sample intervals according to a preset target clustering number and a preset target division ratio; for each sample interval, modifying a sample label located in the sample interval to a first target value within the sample interval.
On the basis of the foregoing embodiment, optionally, the apparatus may further include: the device comprises a parameter setting module, a noise reduction testing module, a training testing module and a determining module;
specifically, the parameter setting module is used for setting a plurality of groups of test parameters, wherein the test parameters comprise initial clustering quantity and initial dividing proportion;
the noise reduction test module is used for performing noise reduction treatment on the sample tags in the original sample data set respectively based on the test parameters to obtain a plurality of test sample data sets;
the training test module is used for training the basic model based on the test sample data set respectively to obtain a plurality of test recommendation models;
the determining module is used for calculating the performance scores of the test recommendation models, and determining the test parameters corresponding to the test recommendation models with the performance scores meeting the preset conditions as the target clustering number and the target division ratio.
On the basis of the above embodiment, optionally, the noise reduction testing module is specifically configured to, for each group of testing parameters, divide the data range formed by all the sample labels into a plurality of testing sample intervals according to the testing parameters; and modifying the sample label in the test sample interval into a second target value in the test sample interval to obtain a test sample data set.
Optionally, the first target value is any one of the following: a median of the sample interval, an average of all sample labels within the sample interval, and a median of all sample labels within the sample interval.
On the basis of the foregoing embodiment, optionally, the recommending module 703 is specifically configured to sort the predicted behavior data and recommend information to the current user according to a sorting result.
Referring now to FIG. 8, shown is a schematic diagram of an electronic device 900 suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 8, the electronic device 900 may include a processing means (e.g., central processing unit, graphics processor, etc.) 901 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage device 906 into a Random Access Memory (RAM) 903. In the RAM903, various programs and data necessary for the operation of the electronic apparatus 900 are also stored. The processing apparatus 901, the ROM 902, and the RAM903 are connected to each other through a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
Generally, the following devices may be connected to the I/O interface 905: input devices 906 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 909 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 906 including, for example, tape, hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic apparatus 900 to perform wireless or wired communication with other apparatuses to exchange data. While fig. 8 illustrates an electronic device 900 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 909, or installed from the storage device 906, or installed from the ROM 902. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing apparatus 901.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring at least two internet protocol addresses; sending a node evaluation request comprising the at least two internet protocol addresses to node evaluation equipment, wherein the node evaluation equipment selects the internet protocol addresses from the at least two internet protocol addresses and returns the internet protocol addresses; receiving an internet protocol address returned by the node evaluation equipment; wherein the obtained internet protocol address indicates an edge node in the content distribution network.
Alternatively, the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving a node evaluation request comprising at least two internet protocol addresses; selecting an internet protocol address from the at least two internet protocol addresses; returning the selected internet protocol address; wherein the received internet protocol address indicates an edge node in the content distribution network.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In one embodiment, there is also provided an information recommendation apparatus comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended;
inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and recommending information to the current user according to each piece of predicted behavior data.
In one embodiment, there is also provided a computer readable storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:
acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended;
inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and recommending information to the current user according to each piece of predicted behavior data.
The information recommendation device, the information recommendation apparatus, and the storage medium provided in the above embodiments may be adapted to perform the information recommendation method provided in any embodiment of the present invention, and have corresponding functional modules and beneficial effects for performing the method. Technical details that are not described in detail in the above embodiments may be referred to an information recommendation method provided in any embodiment of the present invention.
According to one or more embodiments of the present disclosure, there is provided an information recommendation method including:
acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended;
inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and recommending information to the current user according to each piece of predicted behavior data.
According to one or more embodiments of the present disclosure, there is provided the information recommendation method as above, further including:
the method comprises the steps of obtaining an original sample data set, wherein the original sample data set comprises a plurality of sample labels, and the sample labels are behavior data generated by a sample user on display information;
denoising all the sample labels to obtain a denoised sample data set;
and training a preset basic model according to the sample data set subjected to noise reduction processing to obtain the recommendation model.
According to one or more embodiments of the present disclosure, there is provided the information recommendation method as above, further including: dividing a data range formed by all sample labels into a plurality of sample intervals according to the preset target clustering number and the preset target division ratio; for each sample interval, modifying a sample label located in the sample interval to a first target value within the sample interval.
According to one or more embodiments of the present disclosure, there is provided the information recommendation method as above, further including: setting a plurality of groups of test parameters, wherein the test parameters comprise initial clustering quantity and initial dividing proportion; respectively based on the test parameters, carrying out noise reduction processing on the sample labels in the original sample data set to obtain a plurality of test sample data sets; training the basic model based on the test sample data set respectively to obtain a plurality of test recommendation models; and calculating the performance scores of the test recommendation models, and determining the test parameters corresponding to the test recommendation models with the performance scores meeting preset conditions as the target clustering quantity and the target division ratio.
According to one or more embodiments of the present disclosure, there is provided the information recommendation method as above, further including: for each group of test parameters, dividing a data range formed by all sample labels into a plurality of test sample intervals according to the test parameters; and modifying the sample label in the test sample interval into a second target value in the test sample interval to obtain a test sample data set.
Optionally, the first target value is any one of the following: a median of the sample interval, an average of all sample labels within the sample interval, and a median of all sample labels within the sample interval.
According to one or more embodiments of the present disclosure, there is provided the information recommendation method as above, further including: and sequencing the predicted behavior data, and recommending information to the current user according to the sequencing result.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. An information recommendation method, comprising:
acquiring user characteristics of a current user and information characteristics of each piece of information to be recommended;
inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and recommending information to the current user according to each piece of predicted behavior data.
2. The method according to claim 1, wherein before the obtaining of the user characteristics of the current user and the information characteristics of each piece of information to be recommended, the method further comprises:
the method comprises the steps of obtaining an original sample data set, wherein the original sample data set comprises a plurality of sample labels, and the sample labels are behavior data generated by a sample user on display information;
denoising all the sample labels to obtain a denoised sample data set;
and training a preset basic model according to the sample data set subjected to noise reduction processing to obtain the recommendation model.
3. The method of claim 2, wherein the denoising all sample labels comprises:
dividing a data range formed by all sample labels into a plurality of sample intervals according to the preset target clustering number and the preset target division ratio;
for each sample interval, modifying a sample label located in the sample interval to a first target value within the sample interval.
4. The method of claim 3, wherein the determining of the target cluster number and the target partition ratio comprises:
setting a plurality of groups of test parameters, wherein the test parameters comprise initial clustering quantity and initial dividing proportion;
respectively based on the test parameters, carrying out noise reduction processing on the sample labels in the original sample data set to obtain a plurality of test sample data sets;
training the basic model based on the test sample data set respectively to obtain a plurality of test recommendation models;
and calculating the performance scores of the test recommendation models, and determining the test parameters corresponding to the test recommendation models with the performance scores meeting preset conditions as the target clustering quantity and the target division ratio.
5. The method of claim 4, wherein the denoising the sample labels in the original sample data set based on the test parameters, respectively, to obtain a plurality of test sample data sets, comprises:
for each group of test parameters, dividing a data range formed by all sample labels into a plurality of test sample intervals according to the test parameters;
and modifying the sample label in the test sample interval into a second target value in the test sample interval to obtain a test sample data set.
6. A method according to claim 3, wherein the first target value is any one of:
a median of the sample interval, an average of all sample labels within the sample interval, and a median of all sample labels within the sample interval.
7. The method according to any one of claims 1 to 6, wherein the recommending information to the current user according to each predicted behavior data comprises:
and sequencing the predicted behavior data, and recommending information to the current user according to the sequencing result.
8. An information recommendation apparatus, comprising:
the first acquisition module is used for acquiring the user characteristics of the current user and the information characteristics of each piece of information to be recommended;
the prediction module is used for inputting the user characteristics and the information characteristics into a preset recommendation model to obtain predicted behavior data of the current user on each piece of information to be recommended, wherein the recommendation model is obtained by training based on a sample data set subjected to noise reduction processing;
and the recommending module is used for recommending information to the current user according to each piece of predicted behavior data.
9. An electronic device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110185074.7A CN112836128A (en) | 2021-02-10 | 2021-02-10 | Information recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110185074.7A CN112836128A (en) | 2021-02-10 | 2021-02-10 | Information recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112836128A true CN112836128A (en) | 2021-05-25 |
Family
ID=75933572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110185074.7A Pending CN112836128A (en) | 2021-02-10 | 2021-02-10 | Information recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112836128A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327133A (en) * | 2021-06-15 | 2021-08-31 | 北京百度网讯科技有限公司 | Data recommendation method, data recommendation device, electronic equipment and readable storage medium |
| CN113360773A (en) * | 2021-07-07 | 2021-09-07 | 脸萌有限公司 | Recommendation method and device, storage medium and electronic equipment |
| CN113486982A (en) * | 2021-07-30 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Model training method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993638A (en) * | 2019-05-05 | 2019-07-09 | 重庆天蓬网络有限公司 | Method, apparatus, medium and the electronic equipment of Products Show |
| CN110619585A (en) * | 2019-08-16 | 2019-12-27 | 广州越秀金融科技有限公司 | Method, device, storage medium and processor for recommending data |
| CN110704728A (en) * | 2019-09-06 | 2020-01-17 | 北京达佳互联信息技术有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN111310053A (en) * | 2020-03-03 | 2020-06-19 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111681059A (en) * | 2020-08-14 | 2020-09-18 | 支付宝(杭州)信息技术有限公司 | Training method and device of behavior prediction model |
-
2021
- 2021-02-10 CN CN202110185074.7A patent/CN112836128A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993638A (en) * | 2019-05-05 | 2019-07-09 | 重庆天蓬网络有限公司 | Method, apparatus, medium and the electronic equipment of Products Show |
| CN110619585A (en) * | 2019-08-16 | 2019-12-27 | 广州越秀金融科技有限公司 | Method, device, storage medium and processor for recommending data |
| CN110704728A (en) * | 2019-09-06 | 2020-01-17 | 北京达佳互联信息技术有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN111310053A (en) * | 2020-03-03 | 2020-06-19 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111681059A (en) * | 2020-08-14 | 2020-09-18 | 支付宝(杭州)信息技术有限公司 | Training method and device of behavior prediction model |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327133A (en) * | 2021-06-15 | 2021-08-31 | 北京百度网讯科技有限公司 | Data recommendation method, data recommendation device, electronic equipment and readable storage medium |
| CN113360773A (en) * | 2021-07-07 | 2021-09-07 | 脸萌有限公司 | Recommendation method and device, storage medium and electronic equipment |
| CN113486982A (en) * | 2021-07-30 | 2021-10-08 | 北京字节跳动网络技术有限公司 | Model training method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944481B (en) | Method and apparatus for generating information | |
| CN112836128A (en) | Information recommendation method, device, equipment and storage medium | |
| CN107862339B (en) | Method and apparatus for outputting information | |
| CN110619078B (en) | Method and device for pushing information | |
| CN113592535B (en) | Advertisement recommendation method and device, electronic equipment and storage medium | |
| CN112650841A (en) | Information processing method and device and electronic equipment | |
| US20190147540A1 (en) | Method and apparatus for outputting information | |
| CN111061979A (en) | User label pushing method and device, electronic equipment and medium | |
| CN111222960A (en) | Room source recommendation method and system based on public traffic zone | |
| CN111291071A (en) | Data processing method and device and electronic equipment | |
| CN109978594B (en) | Order processing method, device and medium | |
| CN112860999B (en) | Information recommendation method, device, equipment and storage medium | |
| CN113763077A (en) | Method and apparatus for detecting false trade orders | |
| CN116109374A (en) | Resource bit display method, device, electronic equipment and computer readable medium | |
| CN114926234A (en) | Article information pushing method and device, electronic equipment and computer readable medium | |
| CN113792952A (en) | Method and apparatus for generating a model | |
| CN113220922A (en) | Image searching method and device and electronic equipment | |
| CN111339770A (en) | Method and apparatus for outputting information | |
| CN112734462B (en) | Information recommendation method, device, equipment and medium | |
| CN110688508A (en) | Image-text data expansion method and device and electronic equipment | |
| CN117591048B (en) | Task information processing method, device, electronic equipment and computer readable medium | |
| CN113283115B (en) | Image model generation method and device and electronic equipment | |
| CN116823407B (en) | Product information pushing method, device, electronic equipment and computer readable medium | |
| CN116800834B (en) | Virtual gift merging method, device, electronic equipment and computer readable medium | |
| CN114625876B (en) | Method for generating author characteristic model, method and device for processing author information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |